Author: admin

Warehouse automation and robotization for a logistics company

Logistics Case: Development of warehouse automation and robotization for a logistics company   Business case Your browser does not support the audio element. Print Client The company, which is a logistics operator, approached us with the problem of inefficient and time-consuming order processing and route planning processes and to increase productivity by 30%+ Situation Description The company provides express delivery services in major cities and surrounding areas. The company has its own fleet of 70 cars and 18 trucks. Every day the company processes about 500 orders for delivery of various cargoes – from documents to household appliances. Recently, the company has faced problems in logistics due to the growing number of orders: Manual route planning, resulting in suboptimal routes and fuel overruns Long processing time for each order due to manual data entry Frequent errors in order processing resulting in delivery delays Customer complaints due to failure to meet delivery deadlines To solve these problems, the company decided to automate logistics processes. It is planned to implement a route optimization system, a real-time order control system, and partial automation of order processing using RPA. It is expected to increase the speed of order processing by 30% and reduce logistics costs by 10-15%. Supplemental Data: The company has 2 logistics warehouses of 500 m2 and 300 m2 respectively. The warehouses are used for receiving, sorting and picking goods for delivery. Average time of cargo storage in the warehouse is 2 days. The maximum capacity of the warehouses is 1500 cargo places. Warehouse equipment: racks, cargo carts, conveyor, 2 packing machines. Warehouse staff – 12 people (storekeepers, loaders, managers). The average cost of maintaining warehouses is $5000 per month. Types of cargo – documents, household appliances, groceries, clothing, etc. Average delivery distance – 15-20 km Number of drivers – 60 persons Average fuel consumption per day – $500 per day Manual order processing – 15 min per order 5% of errors during order processing Average downtime due to sub-optimal routes – 1.5 h/day – 1.5 h/day Average weight of 1 load – 15 kg Maximum load capacity of 1 car – 500 kg Average distance between delivery points – 5-7 km Number of orders per month – 15 000 Average cost to maintain 1 car – $300 per month Driver salary expenses – $15,000 per month Penalties for failure to meet delivery deadlines – $200 per month Losses due to return of damaged cargo – $1000 per month                                           Exhibit 1 Problem Robotic Process Automation (RPA) To automate routine order processing tasks, it is proposed to implement RPA – robotic process automation. This will reduce the order processing time to 5 minutes and avoid errors when entering data. Intelligent route optimization system A system based on machine learning algorithms will be developed, which will make it possible to optimize routes taking into account the real traffic situation. It is expected to reduce fuel overconsumption by 10-15%. Real-time logistics control system Integrating logistics systems with GPS tracking and mobile apps will provide real-time monitoring. This will eliminate delays and improve service quality. Dictionary Key Terms Forecasting and planning system: a system that enables a company to forecast demand for its products and services and to plan production, distribution and marketing.Forecasting: the process of estimating future values of variables.Planning: the process of developing the actions to be taken to achieve desired results.Forecast accuracy: the degree of closeness of the predicted value to the actual value.Investment payback period: the period of time over which an investment is recouped.Sales conversion: the ratio of successful sales to total sales.Data analysis: the process of collecting, processing and interpreting data.Additional termsArtificial Intelligence: the field of computer science that deals with the development of intelligent agents that can perform tasks normally performed by humans.Machine learning: a field of artificial intelligence that is concerned with developing algorithms that can learn from data without explicit programming.Deep learning: a section of machine learning that uses artificial neural networks to solve complex problems.Case study: a method of learning that involves learning from case studies or examples. Abbreviation  RMSE: Root Mean Square Error.KPI: Key Performance Indicator.AI: Artificial Intelligence.ML: Machine Learning.DL: Deep Learning.CMS: Customer Relationship Management.CRM: Customer Relationship Management.ERP: Enterprise Resource Planning.MRP: Material Requirements Planning.SCM: Supply Chain Management. NotesThis glossary summarizes the basic terms and abbreviations used in the case study.For a more detailed understanding of the case, it is recommended to read additional literature on forecasting and planning systems, machine learning and data analysis.  Marrbery Research Based on our analysis of Delivery’s current logistics processes, our team identified opportunities to optimize them using modern technology. We propose to introduce a routing system based on artificial intelligence. It will make it possible to automatically build optimal routes taking into account traffic conditions in real time. The RPA system is also recommended to automate order processing and eliminate errors. Expected effect: Reduction of logistics costs by 15% 3 times faster order processing Reduction of errors in order processing to 0% Prior to implementation, we will audit your IT infrastructure and business processes to integrate your systems. We will also develop a change management plan to minimize risk and ensure smooth operations during the transition to new systems. Staff training on the new systems is planned for successful implementation. Additional technical details of the solution A multivariate machine learning model based on linear regression was used for demand forecasting. The factors included in the model were: product price, marketing costs, seasonality, competitor sales volume, etc. Gradient descent was used to train the model with adaptive training coefficients to accelerate convergence. Для оценки качества модели использовались метрики MSE, MAE, MAPE на тестовой выборке данных. MSE, MAE, and MAPE metrics were used to evaluate the quality of the model on a test sample of data.The values of these metrics were compared to the baseline forecast. The neural network architecture for prediction included 2 hidden layers of 100 neurons each with

RPA implementation in the bank

Technology Case: RPA implementation in a bank   Business case Your browser does not support the audio element. Print Client The client is one of the leading banks in Ukraine with a network of 300 branches across the country. The Bank provides a full range of financial services for both individuals and legal entities. The bank has a client base of over 800,000+ customers. Situation Description The company found serious problems due to a lot of manual work, especially in document processing. This caused numerous errors, delays and customer complaints. In addition, the cost of maintaining a large workforce was significant. In response to these challenges, a strategy was developed to automate routine processes in the bank. The main objective was to increase productivity and reduce errors. The way to achieve this goal included implementing advanced technologies and optimizing workflows. After implementing this strategy, the bank recorded a marked improvement in productivity as well as a significant increase in customer satisfaction. In addition, staff costs were significantly reduced, which helped to address costs and efficiently utilize the company’s resources. Supplemental Data: The bank processes more than 1 million transactions daily 600 employees are engaged in manual processing Average time to open an account – 2 days, target – 20 minutes Annual IT and data processing maintenance costs – $25 million 10% of customers file complaints due to slow data processing New product introduction takes 3-4 months on average It takes an average of 15 minutes to process one document Goal is to reduce manual data processing by 80%                                           Exhibit 1 Problem 80% of account opening transactions were performed manually, taking up to 3 days per customer More than 50K documents were processed manually by tellers on a daily basis Due to human error rate of up to 10% in manual processing Data processing staffing costs were over $5M per year Due to transaction processing delays, the level of customer complaints increased by 20% over the last year Time to market for new products increased due to lengthy data verification processes Dictionary Key Terms Forecasting and planning system: a system that enables a company to forecast demand for its products and services and to plan production, distribution and marketing.Forecasting: the process of estimating future values of variables.Planning: the process of developing the actions to be taken to achieve desired results.Forecast accuracy: the degree of closeness of the predicted value to the actual value.Investment payback period: the period of time over which an investment is recouped.Sales conversion: the ratio of successful sales to total sales.Data analysis: the process of collecting, processing and interpreting data.Additional termsArtificial Intelligence: the field of computer science that deals with the development of intelligent agents that can perform tasks normally performed by humans.Machine learning: a field of artificial intelligence that is concerned with developing algorithms that can learn from data without explicit programming.Deep learning: a section of machine learning that uses artificial neural networks to solve complex problems.Case study: a method of learning that involves learning from case studies or examples. Abbreviation  RMSE: Root Mean Square Error.KPI: Key Performance Indicator.AI: Artificial Intelligence.ML: Machine Learning.DL: Deep Learning.CMS: Customer Relationship Management.CRM: Customer Relationship Management.ERP: Enterprise Resource Planning.MRP: Material Requirements Planning.SCM: Supply Chain Management. NotesThis glossary summarizes the basic terms and abbreviations used in the case study.For a more detailed understanding of the case, it is recommended to read additional literature on forecasting and planning systems, machine learning and data analysis.  Marrbery Research Our team conducted a thorough analysis of the bank’s existing processes to identify opportunities for optimization through RPA: Audit and measurement of all key business processes in the bank Analysis of the level of process automation and staff time utilization Estimating the cost of manual document and data processing operations Prioritize processes for automation based on volume and cost Benchmarking of RPA best practices in the financial sector Developing the concept of the bank’s target operating model based on RPA This comprehensive research provided us with the data we needed to design the optimal RPA implementation solution for the client. Additional technical details of the solution A multivariate machine learning model based on linear regression was used for demand forecasting. The factors included in the model were: product price, marketing costs, seasonality, competitor sales volume, etc. Gradient descent was used to train the model with adaptive training coefficients to accelerate convergence. Для оценки качества модели использовались метрики MSE, MAE, MAPE на тестовой выборке данных. MSE, MAE, and MAPE metrics were used to evaluate the quality of the model on a test sample of data.The values of these metrics were compared to the baseline forecast. The neural network architecture for prediction included 2 hidden layers of 100 neurons each with ReLU activation function. Optimization was performed using the Adam algorithm. Purpose Automating manual routine processes with RPA to improve the bank’s operational efficiency Implement robotic process automation to optimize data processing and reduce bank costs Build a digital automation platform based on RPA to transform the bank’s operating model Increase data processing productivity by 2x with robotic automation implementation Reduce manual labor in the bank’s key business processes by 70% by implementing RPA Accelerate document processing by 3 times and reduce errors by 50% by implementing digitalization Solution development After defining the problem and its scope, the next step is to develop a solution to solve it. In the case of a bank, this means developing an RPA implementation plan. The RPA implementation plan should include the following key steps: Analysis of existing processes Prioritizing processes for automation Robot development Introduction of robots Robot support and maintenance Analysis of existing processes The first step is to analyze existing processes to determine their suitability for automation. This analysis includes the following tasks: Measuring the volume and cost of manual operations Analyzing the level of process automation Identify problems and challenges associated with manual processes Prioritizing processes for automation The second

Improving the competitiveness of pharmaceutical production

Pharmaceuticals Case: Improving the competitiveness of pharmaceutical production   Business case Your browser does not support the audio element. Print Client Pharma is a leading manufacturer of pharmaceuticals and medical devices. Annual production volume is 2 mln packs of products worth $50 mln. Situation Description The company faced the challenges of rising costs, outdated production processes and increased competition. This led to declining profitability and loss of market share. The company set an ambitious task for Marrbery – to develop a comprehensive strategy for transforming operations to achieve a sustainable competitive advantage in the pharmaceutical market. Our team started to thoroughly analyze the situation and develop innovative solutions for optimization, automation and digitalization of PharmEco’s production and business processes. The goal was to achieve a qualitative leap in the company’s efficiency and competitiveness. Supplemental Data: Production volume – 5 mln packs of pharmaceuticals per year Revenue – $45 million a year Number of personnel – 560 persons Production capacities – 3 plants in different regions of the country Export share – 20% of total volume Main markets – Ukraine, EU and Middle East countries Key competitors – PharmTech, PharmEffect, Ramefarm Logistics costs account for 15% of revenue Warehouse and equipment maintenance costs $2 million per year 60% of equipment has a service life of more than 10 years                                           Exhibit 1 Problem High operating costs due to outdated production assets and inefficient processes Insufficient level of automation and digitalization of production Long cycle of production and bringing new products to market Ineffective supply chain planning and management system Lack of a comprehensive approach to product quality management Insufficient investment in R&D for the development of innovative drugs Loss of market share due to uncompetitive pricing policy Outdated personnel motivation system hindering productivity improvement Dictionary Key Terms Forecasting and planning system: a system that enables a company to forecast demand for its products and services and to plan production, distribution and marketing.Forecasting: the process of estimating future values of variables.Planning: the process of developing the actions to be taken to achieve desired results.Forecast accuracy: the degree of closeness of the predicted value to the actual value.Investment payback period: the period of time over which an investment is recouped.Sales conversion: the ratio of successful sales to total sales.Data analysis: the process of collecting, processing and interpreting data.Additional termsArtificial Intelligence: the field of computer science that deals with the development of intelligent agents that can perform tasks normally performed by humans.Machine learning: a field of artificial intelligence that is concerned with developing algorithms that can learn from data without explicit programming.Deep learning: a section of machine learning that uses artificial neural networks to solve complex problems.Case study: a method of learning that involves learning from case studies or examples. Abbreviation  RMSE: Root Mean Square Error.KPI: Key Performance Indicator.AI: Artificial Intelligence.ML: Machine Learning.DL: Deep Learning.CMS: Customer Relationship Management.CRM: Customer Relationship Management.ERP: Enterprise Resource Planning.MRP: Material Requirements Planning.SCM: Supply Chain Management. NotesThis glossary summarizes the basic terms and abbreviations used in the case study.For a more detailed understanding of the case, it is recommended to read additional literature on forecasting and planning systems, machine learning and data analysis.  Marrbery Research During the research phase of the study, our team conducted: Benchmarking of best automation practices at pharmaceutical production facilities Audit of Pharma’s production facilities to identify bottlenecks Analysis of raw materials consumption rates for optimization Assessment of the potential for digitalization and adoption of advanced technologies Mapping current business processes and identifying inefficient operations Supply chain analysis and optimization opportunities Study of the best HR practices for increasing staff motivation Comparative analysis of the new product development cycle with competitors Study of supply and demand trends in the pharmaceutical market Additional technical details of the solution A multivariate machine learning model based on linear regression was used for demand forecasting. The factors included in the model were: product price, marketing costs, seasonality, competitor sales volume, etc. Gradient descent was used to train the model with adaptive training coefficients to accelerate convergence. Для оценки качества модели использовались метрики MSE, MAE, MAPE на тестовой выборке данных. MSE, MAE, and MAPE metrics were used to evaluate the quality of the model on a test sample of data.The values of these metrics were compared to the baseline forecast. The neural network architecture for prediction included 2 hidden layers of 100 neurons each with ReLU activation function. Optimization was performed using the Adam algorithm. Purpose Reduction of production costs by 20% Reduction of TIME-TO-MARKET by 30% Increase in labor productivity by 25% Market share growth by 5% Solution development Our team proposed a comprehensive transformation strategy that included the following key initiatives: Modernization of production assets by purchasing modern equipment and automated lines. This will increase productivity, reduce rejects and equipment maintenance costs. Implementation of MES and IIoT to automate data collection, quality control and TP optimization. Best practices in machine learning and predictive analytics will be applied. Supply chain optimization based on modeling and data analysis using the SCOR platform. Re-engineering of warehousing and transportation processes. Deploy Lean Manufacturing and TRM program to identify and eliminate inefficient operations, reduce inventory and downtime. Implement CRM system and digital tools to automate marketing, sales and service. Increasing customer loyalty. We utilize advanced change implementation methodologies, risk management and KPIs to successfully implement strategy and achieve targeted results. Decision tree Evaluation Criteria: Labor productivity Flexible production Implementation costs Payback time GMP compliance Alternatives: Mechatronic modular lines Classical automation based on PLCs and SCADA Hybrid solution using industrial robots Integrated automation with MES and IIoT Analysis: High productivity but limited flexibility, high costs Low start-up costs, but limited scalability Flexibility due to robots, but high cost of implementation Maximum return, but high initial investment and complexity Solution: Complex automation (4) with phased implementation and pilot projects. appendix 1 Our analysis shows that given the high material intensity of these areas and the volatility of

Development of innovative ecological packaging

Packaging Case : Development of innovative ecological packaging   Business case Your browser does not support the audio element. Print Client Packaging manufacturer – aims to develop and implement more environmentally friendly and sustainable packaging for its products. The main objective is to reduce the negative impact on the natural environment and increase the renewability of the materials used in the production of packaging.  Situation Description “The client is a leading manufacturer of packaging for various industries including food, pharmaceutical and cosmetics. Its annual production exceeds 5 million units and revenues are over $15 million. However, a major concern is the negative environmental impact of traditional carton packaging and the difficulty of waste disposal. At the same time, consumers and the market are increasingly demanding eco-friendly packaging solutions, which could negatively impact the company’s competitiveness.” The company challenged MARRBERY to develop more environmentally friendly types of paperboard packaging that are in line with sustainability principles.  Supplemental Data: The company’s market share is 15% of the total carton packaging production in the country 80% of production is exported to EU countries Waste disposal costs $200,000 per year Packaging sustainability requirements are tightened by 10% annually Demand for eco-packaging has grown by 40% in the last 3 years Target to reduce the carbon footprint of packaging by 20% 60% of consumers are willing to pay more for sustainable packaging €50 million investment available in the EU for green packaging projects                                           Exhibit 1 Problem High negative environmental impact of traditional carton packaging Difficulties of cardboard waste disposal and recycling Failure of traditional packaging to meet growing environmental and sustainability requirements Lagging behind competitors that are already implementing eco-packaging Risk of losing customers who demand more environmentally friendly packaging Insufficient investment in R&D to develop innovative eco-solutions Lack of competence in environmental packaging Negative impact on the company’s reputation due to outdated, non-environmental Dictionary Key Terms Forecasting and planning system: a system that enables a company to forecast demand for its products and services and to plan production, distribution and marketing.Forecasting: the process of estimating future values of variables.Planning: the process of developing the actions to be taken to achieve desired results.Forecast accuracy: the degree of closeness of the predicted value to the actual value.Investment payback period: the period of time over which an investment is recouped.Sales conversion: the ratio of successful sales to total sales.Data analysis: the process of collecting, processing and interpreting data.Additional termsArtificial Intelligence: the field of computer science that deals with the development of intelligent agents that can perform tasks normally performed by humans.Machine learning: a field of artificial intelligence that is concerned with developing algorithms that can learn from data without explicit programming.Deep learning: a section of machine learning that uses artificial neural networks to solve complex problems.Case study: a method of learning that involves learning from case studies or examples. Abbreviation  RMSE: Root Mean Square Error.KPI: Key Performance Indicator.AI: Artificial Intelligence.ML: Machine Learning.DL: Deep Learning.CMS: Customer Relationship Management.CRM: Customer Relationship Management.ERP: Enterprise Resource Planning.MRP: Material Requirements Planning.SCM: Supply Chain Management. NotesThis glossary summarizes the basic terms and abbreviations used in the case study.For a more detailed understanding of the case, it is recommended to read additional literature on forecasting and planning systems, machine learning and data analysis.  Marrbery Research Our team of experts conducted a thorough research to address the Analysis of the environmental packaging market and best global practices Technological audit of the company’s eco-packaging capabilities Exploring the latest biodegradable and recyclable materials for packaging Consumer survey on the demand for green packaging Assessment of carbon footprint and opportunities for its optimization Analysis of legislative requirements and trends in the field of ecological packaging Benchmarking the best eco-solutions of competitors Determining how best to achieve the client’s sustainability goals Expected effect: Reducing environmental impact by moving towards biodegradable and recycled materials in packaging production. Reduce carbon footprint by optimizing manufacturing processes and using greener materials. Increasing the company’s competitiveness by producing an environmentally friendly product that meets modern standards and market requirements. Improved brand perception among consumers as an environmentally responsible producer. Increasing the company’s innovation potential and entering new markets where a high degree of sustainability is a key selection factor. Opportunities for financial incentives or government assistance for companies that actively promote environmental safety and sustainability. Improved relations with partners and customers, as more and more companies are showing interest in cooperating with environmentally responsible producers. Planned for successful implementation. Development and testing of new materials: Conducting research and experiments to create biodegradable and recyclable materials that meet quality and safety standards. Modernization of production processes: Introduction of new technologies and equipment to optimize production of ecological packaging. Testing in practice: Conducting test production and testing of environmental packaging to verify its functionality and reliability. Market Reaction Study: Market research and analysis of consumer reaction to a new product. Launch of mass production: Start of production of ecological packaging on a commercial scale. Marketing and Sales: Develop marketing and sales strategy for new packaging, including market promotion and customer acquisition. Monitoring and optimization: Continuously monitoring the quality and effectiveness of new packaging and looking for opportunities to further improve it. Additional technical details of the solution A multivariate machine learning model based on linear regression was used for demand forecasting. The factors included in the model were: product price, marketing costs, seasonality, competitor sales volume, etc. Gradient descent was used to train the model with adaptive training coefficients to accelerate convergence. Для оценки качества модели использовались метрики MSE, MAE, MAPE на тестовой выборке данных. MSE, MAE, and MAPE metrics were used to evaluate the quality of the model on a test sample of data.The values of these metrics were compared to the baseline forecast. The neural network architecture for prediction included 2 hidden layers of 100 neurons each with ReLU activation function. Optimization was performed using the Adam algorithm. Purpose Develop new 100% eco-friendly packaging

Developing strategies for an agricultural enterprise

Agriculture Case: Developing strategies for an agricultural enterprise   Business case Your browser does not support the audio element. Print it out Сlient Our client is a company a national producer of crop products using vertical farm technology, turned to Marrbery for help to improve the efficiency of business processes and increase profitability 45% +  Situation Description A vertically integrated company specializing in the cultivation and marketing of agricultural products. Control over the entire production cycle provides the company with complete control over the quality of its products. However, the company faced some challenges. Inefficient resource management and low labor productivity resulted in sub-optimal resource utilization. Current key performance indicators do not reflect the full picture of the company’s performance. Logistics costs were well above industry standard norms. To address these challenges, the company turned to Marrbery. The task was to conduct an in-depth analysis of the company’s operations and develop a strategy aimed at optimizing business processes and improving performance indicators.   Total area of agricultural land: 5,000 hectares. Types of production: cereals, vegetables, fruits, milk, meat (specify which specific crops the company grows). Production facilities: own storage facilities, warehouses, farm complexes. Geography of activity: regional market, supplies to neighboring regions. Number of employees: 200 people. Own vehicle fleet: 15 trucks. Average annual turnover: $8 million dollars. Number of regular partners (restaurants, stores): 50. Used modern technologies in agriculture (for example: irrigation systems, weather monitoring, automated fertilizer systems).  Exhibit 1 Problem: Lack of effective production management and resource planning Low labor productivity High logistics costs Lack of KPIs for performance evaluation Dictionary Key Terms Forecasting and planning system: a system that enables a company to forecast demand for its products and services and to plan production, distribution and marketing.Forecasting: the process of estimating future values of variables.Planning: the process of developing the actions to be taken to achieve desired results.Forecast accuracy: the degree of closeness of the predicted value to the actual value.Investment payback period: the period of time over which an investment is recouped.Sales conversion: the ratio of successful sales to total sales.Data analysis: the process of collecting, processing and interpreting data.Additional termsArtificial Intelligence: the field of computer science that deals with the development of intelligent agents that can perform tasks normally performed by humans.Machine learning: a field of artificial intelligence that is concerned with developing algorithms that can learn from data without explicit programming.Deep learning: a section of machine learning that uses artificial neural networks to solve complex problems.Case study: a method of learning that involves learning from case studies or examples. Abbreviation  RMSE: Root Mean Square Error.KPI: Key Performance Indicator.AI: Artificial Intelligence.ML: Machine Learning.DL: Deep Learning.CMS: Customer Relationship Management.CRM: Customer Relationship Management.ERP: Enterprise Resource Planning.MRP: Material Requirements Planning.SCM: Supply Chain Management. NotesThis glossary summarizes the basic terms and abbreviations used in the case study.For a more detailed understanding of the case, it is recommended to read additional literature on forecasting and planning systems, machine learning and data analysis.  The Marrbury study Based on the results of our analysis of the current state of the company’s business processes, our team of experts has identified a number of opportunities for optimizing production activities using advanced technologies. We propose to implement a comprehensive IIoT-based production monitoring and management system using machine learning and artificial intelligence methods. Implementation of a distributed sensor network will allow collecting and transmitting data from equipment in real time for further analysis. The developed machine learning algorithms will identify hidden regularities, predict KPIs and develop recommendations for optimizing process modes and equipment parameters. The expected economic effect of the system implementation is a 20-25% increase in productivity, a 30% reduction in product scrap, and a 10-15% reduction in logistics costs. Verification of compatibility of the proposed technical solutions with the customer’s existing equipment and IT infrastructure. This will help to avoid problems during system integration and implementation. Development of a detailed change management plan – organizational and technological. The plan should minimize risks and ensure smooth transition of production and business processes to the new system. Conducting training and trainings for the customer’s employees on working with the implemented monitoring and analytics system. This is critical for the successful operation of the system in the long term. Statistical indicators and calculations Statistical indicators and calculations Linear regression:Coefficient of determination R2 = 0.82, which indicates good quality of the modelFisher’s F-statistic = 78.6, the model is significant at the level of p<0.01The RMSE mean square error on the test sample was 120 units Logistic regression: Площадь под кривой ROC = 0.91, что соответствует отличной предсказательной способностиУ модели высокая чувствительность (85%) и специфичность (80%)Коэффициент конкордации на тестовых данных = 0.89, что свидетельствует о сильной связи модели The area under the ROC curve = 0.91, which corresponds to excellent predictive abilityThe model has high sensitivity (85%) and specificity (80%)The concordance coefficient on the test data = 0.89, indicating a strong model relationshipModel Comparison: The XgBoost machine learning model showed 15% lower error compared to linear regression Solution development Carefully moving on to the next stage, we set about analyzing the company’s current business processes. Digging deep into the details, we looked at every aspect – from resource management to logistics. In this whirlwind of data, we identified the core problem, which appeared to be led by a failure to plan for resource requirements.Our hypothesis, backed by careful calculations, was that implementing an ERP system with predictive analytics capabilities would have a revolutionary impact on optimizing planning. We chose methods with proven performance – linear programming for resource optimization and a neural network for accurate yield forecasting.The next step was to develop and successfully implement an ERP system based on the selected mathematical methods. During this phase, we were meticulous in every detail, ensuring that the new technologies were harmoniously integrated into the company’s workflow.Finally, we moved on to the deeper phase of testing the ERP system on real data. This allowed us not only to assess the accuracy of the predictions, but also to make the necessary adjustments to maximize efficiency.Thus, with each stage,

What is the future of work?

Selected analytical information What is the future of work?       Article Your browser does not support the audio element. Download PDF Print The world of work is constantly evolving, and the future of work requires businesses and organizations to take an informed approach. They need to be aware of possible changes in the workplace, given digitalization and other current trends. Particular attention should be paid to preparing the workforce and workplaces for these changes. Artificial intelligence and automation play a significant role in this process, similar to mechanization in the past. When we look at the future of work, we see that it will be different than it is today. Offices may become more flexible and adaptive, with a greater bias toward using technology and working remotely. Robots and automation may play an increasingly important role in production processes, freeing people from routine tasks and allowing them to focus on the more creative and strategic aspects of work. New types of work may emerge that involve the development and implementation of new technologies. The future of work will require flexibility, continuous learning, and adaptation to changing conditions. It is important to be prepared for these changes and actively seek out new opportunities and approaches in the world of work. As part of our analysis, we consider the potential demand for labor and the mix of occupations and skills needed for those jobs. We consider eight countries: China, France, Germany, India, Japan, Spain, the United Kingdom, and the United States. These countries represent different economic and labor market models, which together account for nearly half of the world’s population and more than 60 percent of its GDP. Studying these countries allows us to get a comprehensive picture of labor market trends and assess their impact on the future of the field of work. Here are some of the key findings of the latest report on the future of work: By year 16, one in every 2030 workers may have to change careers. That’s more than 100 million workers in the eight countries studied, and the pandemic has accelerated the expected transition of the workforce. Job growth will be more concentrated in high-skilled jobs (such as health care or science, technology, engineering, and math [STEM] jobs), while medium- and low-skilled jobs (such as catering, manufacturing jobs, or office support roles) will decline. Some occupational categories may see more growth than others. The growth of e-commerce has created demand for warehouse workers; investment in the green economy may increase the need for wind turbine technicians; aging populations in many advanced economies will increase demand for nurses, home care aides and hearing aid specialists; and teachers and training instructors will also continue to find jobs in the coming decade. But other types of jobs may be at risk: as grocery stores increasingly install self-service cash registers, for example, there may be a need for fewer clerks, and robotics used to handle routine paperwork may reduce demand for some office workers. Flexibility and adaptability will be key skills for workers. In the future of the workplace, change will be rapid and unpredictable. Workers who have the ability to adapt quickly to new technologies, work methods, and market demands will be in high demand. Flexibility in thinking, the ability to learn new skills and adapt to different situations will be necessary competencies for a successful career in the future. Overall, the future of the workplace will depend on various factors, such as technological innovations, changes in societal needs, and demographic changes. Workers and organizations must be prepared to adapt and continually learn in order to successfully cope with these changes and find new opportunities in the future field of work. “The Future of Work: Accelerating Pandemic Transformation and Three Key Trends”: Remote work and virtual encounters are likely to continue, though less intensely than at the peak of the pandemic. E-commerce has skyrocketed, increasing two to five times its pre-CoVID-19 numbers, and other types of virtual transactions, such as telemedicine, online banking and streaming entertainment, have taken off. And the move to digital transactions has also contributed to growth in shipping, transportation, and warehousing jobs. Digital Technology, including automation and artificial intelligence. Companies have used them to control costs or mitigate uncertainty; They have also deployed these technologies in warehouses, grocery stores, call centers, and manufacturing sites to either reduce job density or cope with the growing demand for goods. Understanding these macroeconomic trends in the global economy is vital to planning for what lies ahead.                                           Exhibit 1 Generation C (COVID) will have their own characteristics and experiences with the global pandemic. They will witness significant changes in health care, education, technology and social interaction. For example, Generation Alpha is the first generation that did not catch the “pre-Internet” era Predicting specific occupations Predicting specific occupations that will be popular in the future is a difficult task because it depends on many factors, including technological breakthroughs, social trends, and economic changes. However, there are some industries that are likely to have an increased demand for professionals in the future. Here are a few such industries: Information Technology: Advances in technology, artificial intelligence, cloud computing, cybersecurity and big data will drive increased demand for professionals in programming, application development, data analytics and cybersecurity. Health and Medicine: With an increasing aging population and the development of new treatments, the demand for doctors, medical professionals, nurses and pharmacists is expected to last a long time. Energy and renewable energy: With a growing awareness of environmental issues and the need to transition to cleaner energy sources, the demand for renewable energy engineers and sustainability experts could increase significantly. Engineering and Robotics: Advances in automation, artificial intelligence and robotics will create new opportunities in engineering, robotics and process automation.  Cryptocurrencies and blockchain: With the development of digital currencies and blockchain technology, there may be a demand for cryptocurrency experts, blockchain developers

Demand forecasting for cheese production

Food industry Case : Demand Forecasting for Cheese Production   Business case Your browser does not support the audio element.     Download PDF Print Client Our client, a large national cheese producer in Central Europe, approached Marrbery for assistance due to inaccurate demand forecasting for the company’s products, which was losing approximately $200,000 annually due to excess spoilage and shortages of certain items resulting in lost sales. The forecasting models had an error rate of more than 30%. Situation Description MSM is a leading cheese and dairy products company. It is a fully integrated company engaged in the production, marketing and sales of its own cheese brands. It also owns the entire supply chain, including dairy production, laboratories, packaging lines and its own distribution network to retail outlets. With large production facilities spread across different countries and distribution agreements with major retailers, MSM is able to offer a variety of products in the dairy segment. MSM is currently evaluating new products such as lactose-free cheese and Biolife vegan cream cheese. While cheese products are typically targeted at a broad audience, these new products may appeal to certain market segments. “Biolife” is designed with a focus on consumers with lactose intolerance, which is one of the most common food intolerances in the world. In addition, vegans who eliminate animal products from their diet may also be a key target audience for “Biolife.” MSM expects these new products to capitalize on the growing popularity among consumers focused on inclusive and healthy lifestyles. MSM produces 20 types of cheese with a total volume of 50,000 tons per year 60% of production is supplied to retail chains, 40% to independent stores Due to forecast errors, monthly losses amounted to $15-20 thousand. Average forecast error by assortment – 38% Marrbery study The Vice President of Marketing at MSM asked us to analyze key aspects related to the forecasting and launch of the Biolife product. Our task – provide a comprehensive assessment of the factors affecting the success of product introduction to the market, as well as identify MSM’s internal reserves to support this process. Our team conducted the following stages of analysis and development: Sales history analysis: We examined sales data for each product and distribution channel for the last three years in detail. This allowed us to identify trends and seasonal fluctuations in demand.   Statistical forecasting models: We applied advanced statistical methods for time series forecasting, including ARIMA, SARIMA and Prophet. As a result, we achieved an error rate of 22%, which is acceptable.   Machine learning system development: Our experts developed our own machine learning-based forecasting and planning system. This system allows for more accurate forecasting of product demand as well as automating the planning process.   This system allows MSM to improve demand management and optimize the production plan. We are confident that the implementation of this system will bring significant results and increase the efficiency of the company’s cheese production activities.                                           Exhibit 1 Our team developed a machine learning system for demand forecasting using the company’s historical sales data for the past 5 years. We adapted linear regression, neural network and gradient bousting algorithms to the specifics of the client’s data. This allowed us to create an accurate and reliable demand forecasting model. In addition, the system has been successfully integrated with the company’s ERP, ensuring efficient data management. It is important to note that our approach not only considered historical data, but also took into account current market trends and consumer demand characteristics and a multidisciplinary approach in analyzing and forecasting data.  Solution development It is revealed that current forecasts are based on subjective expert assessment. This leads to a high forecast error We hypothesized that applying machine learning models based on actual sales data will significantly improve forecasting accuracy.  Hypotheses: The following hypotheses about the possible causes of prediction errors were initially hypothesized: Incorrect algorithm for calculating the forecast based on expert estimates. Insufficient quality of sales input data. Use of outdated forecasting software. After analyzing the data and the current approach, hypothesis No1 was confirmed – the problem is an incorrect algorithm based on subjective expert opinions. To solve the problem, we proposed to move from expert methods to evidence-based machine learning models. This will significantly reduce the prediction error. Dictionary Key Terms Forecasting and planning system: a system that enables a company to forecast demand for its products and services and to plan production, distribution and marketing.Forecasting: the process of estimating future values of variables.Planning: the process of developing the actions to be taken to achieve desired results.Forecast accuracy: the degree of closeness of the predicted value to the actual value.Investment payback period: the period of time over which an investment is recouped.Sales conversion: the ratio of successful sales to total sales.Data analysis: the process of collecting, processing and interpreting data.Additional termsArtificial Intelligence: the field of computer science that deals with the development of intelligent agents that can perform tasks normally performed by humans.Machine learning: a field of artificial intelligence that is concerned with developing algorithms that can learn from data without explicit programming.Deep learning: a section of machine learning that uses artificial neural networks to solve complex problems.Case study: a method of learning that involves learning from case studies or examples. Abbreviation  RMSE: Root Mean Square Error.KPI: Key Performance Indicator.AI: Artificial Intelligence.ML: Machine Learning.DL: Deep Learning.CMS: Customer Relationship Management.CRM: Customer Relationship Management.ERP: Enterprise Resource Planning.MRP: Material Requirements Planning.SCM: Supply Chain Management. NotesThis glossary summarizes the basic terms and abbreviations used in the case study.For a more detailed understanding of the case, it is recommended to read additional literature on forecasting and planning systems, machine learning and data analysis.  Decision tree Data Analysis: At the beginning of the project, the company’s sales and production data for the past 5 years was collected and analyzed. This included information on cheese types, sales volumes, regional characteristics and

Have you thought about how AI will change the course of history?

Selected analytical information Have you ever wondered how AI will change the course of history?     Article Your browser does not support the audio element.             Download PDF Print Generative AI creates value now. The speed of scaling by properly mobilizing the organization and focusing on value will be far more important than the speed of piloting. AI has infiltrated our lives gradually, through everything from the technology that powers our smartphones to the autonomous driving features on cars to the tools retailers use to surprise and delight consumers. As a result, its progress has been almost invisible. Generative AI systems fall under the broad category of machine learning, and here’s how one such system, ChatGPT, describes what it can do: Ready to take your creativity to the next level? Look no further than generative AI! This nifty form of machine learning allows computers to generate all sorts of new and exciting material, from music and art to entire virtual worlds. And it’s not just for fun-but generative AI has many practical applications, such as creating new products and optimizing business processes. So why wait? Unleash the power of generative AI and see what amazing creations you can come up with! Did anything in this paragraph strike you? Probably not. The grammar is perfect, the tone works, and the narrative flows. That’s why ChatGPT — GPT means a generative pre-trained transformer – which now gets so much attention. It is a free chatbot that can give an answer to almost any question asked of it. Developed by OpenAI and released for testing by the general public in November 2022, it is already considered the best AI chatbot. And it’s popular, too: more than a million people have signed up to use it in just five days. Starry-eyed fans have posted examples of chatbot computer code creation, college-level essays, poems and even halfway decent jokes. Others, among a wide range of people who make their living creating content, from advertising copywriters to full-time professors, are quaking in their boots.                                           Exhibit 1 Users don’t need a degree in machine learning to interact with or derive value from AI; almost anyone who can ask questions can use it. And, as with other breakthrough technologies such as the personal computer or iPhone, a single generative AI platform can create multiple applications for audiences of any age or education level and anywhere with Internet access. How generative AI differs from other types of AI As the name implies, the main way in which generative AI differs from previous forms of AI or analytics is that it can effectively generate new content, often in “unstructured” forms ( such as written text or images) that are not naturally represented in tables with rows and columns (see panel below“ Dictionary ” for a list of terms related to generative AI). Dictionary Application Programming Interface (API) is a way of programmatically accessing (usually external) models, datasets or other software tools. Artificial Intelligence ( AI ) the ability of software to perform tasks that traditionally require human intelligence. In-depth training is a subset of machine learning that uses deep neural networks, which are layers of connected neurons ” whose connections have parameters or weights that can be trained. This is particularly effective in learning unstructured data, such as images, text, and audio. Fine-Tuning is the process of adapting a pre-trained baseline model to perform better in a particular task. It entails a relatively short period of training on a labeled dataset, which is much smaller than the dataset on which the model was originally trained. This additional training allows the model to learn and adapt to the nuances, terminology, and specific patterns found in the smaller dataset. Fundamental Models (FM) are deep learning models trained on huge amounts of unstructured, unlabeled data that can be used for a wide range of tasks out of the box or adapted to specific tasks through fine-tuning. Examples of these models are GPT-4, PaLM, DALL – E 2, and stable diffusion. Generative AI  is an AI that is typically built using foundational models and has capabilities that the AI did not have before, such as the ability to generate content. Foundational models can also be used for non-generative purposes ( e.g., classifying user sentiment as negative or positive based on call transcripts ), offering a significant improvement over earlier models. For simplicity, when we refer to generative AI in this article, we include all variants of the underlying model. Graphics processors ( graphics processors ) are computer chips that were originally designed for the production of computer graphics ( e.g., for video games) and are also useful for deep learning applications. In contrast, traditional machine learning and other analyses are typically performed on central processing units (CPUs) usually referred to as the computer processor. “ Large Language Models (LLMs) constitute a class of basic models that can handle huge amounts of unstructured text and learn relationships between words or parts of words, known as tokens. This allows LLMs to generate natural language text, performing tasks such as generalization or knowledge extraction. GPT-4 ( which underlies ChatGPT ) and LaMDA ( the Bard model ), are examples of LLMs. Machine Learning ( ML ) is a subset of AI in which a model acquires capabilities after learning or showing many examples of data points. Machine learning algorithms detect patterns and learn to make predictions and recommendations by processing data and experiences rather than receiving explicit programming instructions. Algorithms also adapt and can become more efficient in response to new data and experiences. MLOps refers to engineering models and practices for scaling and maintaining AI and ML. It includes a set of practices that span the full ML lifecycle ( data management, development, deployment, and real-time operations ). Many of these practices are now enabled or optimized with

What is design thinking?

Selected analytical information What is design thinking?   Article Your browser does not support the audio element. Download PDF Print Design Thinking is a methodology that helps organizations effectively solve complex problems and create innovative solutions that are focused on customer needs. This approach is based on the inclusion of creative thinking, data analysis, and a strong focus on the user. Design and conquest:In years past, the word “design” might have conjured up images of expensive handbags or glossy coffee tables. Now, your mind can go straight to the point. Design and design thinking are buzzing in the business community more than ever. Until now, design has focused mostly on what something looks like; these days, it’s a dynamic idea used to describe how organizations can adjust their approaches to problem solving to respond to rapidly changing environments and create maximum impact and shareholder value. Design is a journey and a destination. Design thinking is the primary way to start a journey and arrive at the right destination at the right time. design thinking, companies can develop products, services and strategies that better meet the needs and expectations of their customers. This allows organizations to be more agile and innovative in a rapidly changing environment and achieve high performance. Design thinking, is “the greatest competitive advantage you can have if your customers are loyal to you, because if you solve their needs first, you will always win.” А good design – it’s good business. The Value of Design to Business shows that the best designers increase their revenues and investor returns almost twice as fast as their industry peers. Moreover, over a ten-year period, design-oriented companies have outperformed the S&P 500 by 300+ percent.                                               Exhibit 1 As you may have already seen in the illustration, design thinking goes far beyond how something looks. And incorporating design thinking into your business is more than just setting up a design studio and hiring designers. Design thinking means fundamentally changing the way you design your products, services, and, in fact, your organization itself. Want to learn more about our design practices? Marrbery   How do companies build a corporate culture based on design? Success in business is more than just developing a great product or service that generates financial returns. Empathy and purposefulness are basic business needs. Design thinking means that customers, employees and the planet are at the center of problem solving. Marrbery Design has found that design-oriented organizations start with a design-based culture. Here are four steps to success with design: 1. Understand your audience. Design-focused companies go beyond asking what customers and employees want and truly understand why they want it. Design-focused companies often turn to cultural anthropologists and ethnographers to delve into how their customers use and experience products, including what motivates them and what pushes them away. One example is a well-known cosmetics retailer. When marketing leaders actually observed customers using the company’s website, they realized that customers often went to YouTube as well as TikTok to watch videos of people using the products before making a purchase. Using this information, the cosmetics retailer developed its own line of demo videos, keeping customers on the site and therefore more likely to make a purchase. 2. Bring design to the executive table. This leader can be a design director, a digital director, or a marketing director. In general, this leader should be the best advocate for the company’s customers and employees, bringing the perspective of people, planet, and company goals to strategic business decisions. The project manager also has to build bridges between multiple functions and stakeholders, involving different groups in the design iteration process. 3. Design in real time. To understand how and why people – both customers and employees – use processes, products, or services, organizations must develop a three-pronged design thinking model that combines design, business strategy, and technology. This approach enables business leaders to identify trends, co-create using feedback and data, prototype, test, and create governance models for ongoing investments. 4. Act quickly. Good design depends on agility. This means delivering the product to users quickly and then iterating based on customer feedback. In a design-driven culture, companies are not afraid to release products that are not quite perfect. Designers know that there is no end to the design process. The power of design, on the other hand, lies in its ability to accept and adapt as needs change. When designers are embedded in teams, they are uniquely positioned to gather and digest feedback, which can lead to unexpected discoveries. Ultimately, this approach produces more efficient and profitable results than following a prescribed path. Take Instagram, for example. When they launched their first product in 2010, Instagram’s founders focused on the most popular features: sharing images, commenting, and liking. A few months later, they relaunched with a stripped-down version, resulting in 100,000 downloads in less than a week and more than two million users in less than two months – all without any strategic promotion. What is the connection between user-centered design and design thinking? Both processes are based on design. And they both emphasize listening to and deeply understanding users, as well as continuously collecting and implementing feedback to develop, refine, and improve the service.What makes them different is their scale. User-centered design focuses on improving a specific product or service. Design thinking takes a broader view as a way to creatively solve complex problems – whether it’s a startup, a large organization, or society as a whole. User-centered design is great for developing a fantastic product or service. In the past, a company could use a great process or product for years before competitors caught up. But now, with digitalization leading to more frequent and faster disruptions, users need a dynamic mix of products and services. The focus has firmly shifted from features and functions to purpose, lifestyle, and

Market share

< Back to the MARRBERY schedule of the day Market SHARE Telegram Facebook-f Twitter Linkedin-in Medium Instagram Market share is the percentage of a company’s sales or revenues from total sales or revenues in an industry. Market share is an important indicator of a company’s competitiveness and success in the marketplace. Companies can increase their market share by expanding their product offerings, improving the quality of their products and services, attracting new customers, and retaining existing customers. There are several ways to increase market share. For example: Expanding the range of products and servicesImproving the quality of products and servicesAttracting new customers through marketing and advertisingRetaining existing customers through loyalty programs and customer serviceExpanding geographic coverage and entering new marketsReducing prices or offering special promotions and discountsInnovating and implementing new technology Which of these ways do you feel is most appropriate for your business? Terms of Use Privacy Policy